20 papers · ranked by Valyu relevance
Fang Liu, Zhiyi Fu, Ge Li, Zhi Jin + 2 more
Code completion tools are frequently used by software developers to accelerate software development by suggesting the following code elements. Completing a sequence of code tokens (e.g., a full line of code) has been proved more efficient than predicting a single token at a time. To complete the code sequence…
Chaozheng Wang, Junhao Hu, Cuiyun Gao, Jin Yu + 4 more
'Hailiang Huang' 'Zhenyu Lei' 'Yuetang Deng'] Abstract—Code completion has become a common practice for programmers during their daily programming activities. It aims at automatically predicting the next tokens or lines that the programmers tend to use. A good code completion tool can substantially save keystrokes and…
Shamima Naznin, Manishankar Mondal
—Coding is an integral aspect of programming. A programmer can automatically complete a code fragment after writing a few tokens and the process of automatically completing a code fragment is known as code completion. A number of research on code completion have previously been conducted for method body completion and…
Muhammad Hammad, Önder Babur, Hamid Abdul Basit, Mark van den Brand + 1 more
'Yilun Shang'] Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones (similar code fragments) accumulated in these repositories represent often repeated functionalities and are candidates for reuse in an exploratory or rapid development. To facilitate…
Tam The Nguyen, Tung Thanh Nguyen, Le Hoang Son
Code recommendation is an important feature of modern software development tools to improve the productivity of programmers. The current advanced techniques in code recommendation mostly focus on the crowd-based approach. The basic idea is to collect a large pool of available source code, extract the common code…
Anton Semenkin, Vitaliy Bibaev, Yaroslav Sokolov, Kirill Krylov + 13 more
'Alexey Kalina' 'Anna Khannanova' 'Danila Savenkov' 'Darya Rovdo' 'Igor Davidenko' 'Kirill Karnaukhov' 'Maxim Vakhrushev' 'Mikhail Kostyukov' 'Mikhail Podvitskii' 'Petr Surkov' 'Yaroslav Golubev' 'Nikita Povarov' 'Timofey Bryksin'] In this work, we describe our approach for building a multitoken code completion feature…
Anton Semenkin, Yaroslav Sokolov, Evgeniia Vu
Code Completion is one of the most used Integrated Development Environment (IDE) features, which affects the everyday life of a software developer. Modern code completion approaches moved from the composition of several static analysis-based contributors to pipelines that involve neural networks. This change allows the…
Hitesh Sagtani, Rishabh Mehrotra, Beyang Liu
Fill-in-the-Middle (FIM) models play a vital role in code completion tasks, leveraging both prefix and suffix context to provide more accurate and contextually relevant suggestions. This paper presents approaches to improve FIM code completion while addressing the challenge of maintaining low latency for real-time…
Vijayaraghavan Murali, Chandra Maddila, Imad Ahmad, Michael Bolin + 5 more
'Daniel Cheng' 'Negar Ghorbani' 'Renuka Fernandez' 'Nachiappan Nagappan' 'Peter C. Rigby'] VIJAYARAGHAVAN MURALI, Meta Platforms Inc., USA CHANDRA MADDILA, Meta Platforms Inc., USA IMAD AHMAD, Meta Platforms Inc., USA MICHAEL BOLIN, Meta Platforms Inc., USA DANIEL CHENG, Meta Platforms Inc., USA NEGAR GHORBANI, Meta…
Michael Yarus
Preexisting partial genetic codes can fuse to evolve toward the Standard Genetic Code (SGC). Code fusion provides a path of least selection, generating a code precursor that resembles the SGC, consequently evolving quickly. Optimal evolution requires wobble coding delayed until late in primordial codon assignment…
Anastasia Drozdova, Ekaterina Trofimova, Polina Guseva, Anna Scherbakova + 2 more
The use of program code as a data source is increasingly expanding among data scientists. The purpose of the usage varies from the semantic classification of code to the automatic generation of programs. However, the machine learning model application is somewhat limited without annotating the code snippets. To address…
Authors not listed
Bayesian optimization (BO) has become increasingly important for experimental optimization across scientific domains, yet implementing BO pipelines requires significant programming expertise and familiarity with specialized frameworks. This creates a barrier for domain experts who could benefit from BO but lack the…
Pieter Floris Jacobs, Robert Pollice
Scientists across domains are often challenged to master domain-specific languages (DSLs) for their research, which are merely a means to an end but are pervasive in fields like computational chemistry. Automated code generation promises to overcome this barrier, allowing researchers to focus on their core expertise.…
Itamar Lachman, Irit Hadar, Uri Hertz
Recent research shows that people usually try to avoid exerting cognitive effort yet they are willing to exert effort to gain rewards. This cost-benefit framework provides predictions for behaviour outside the laboratory. Nevertheless, the extent to which such considerations affect real-life decisions is not clear.…
Jacqueline A Jansen, Artür Manukyan, Nour Al Khoury, Altuna Akalin
Data analysis is constrained by a shortage of skilled experts, particularly in biology, where detailed data interpretation is vital for understanding complex biological processes and developing new treatments and diagnostics. To address this, we developed mergen, an R package that leverages Large Language Models (LLMs)…
Chonghuan Zhang, Adarsh Arun, Alexei Lapkin
Computer Aided Synthesis Planning (CASP) development of reaction routes requires understanding of complete reaction structures. However, most reactions in the current databases are missing reaction co-participants. Although reaction prediction and atom mapping tools can predict major reaction participants and trace…
Yiwen Zhang, Wei Liu, Fazhong Jiang, Jiquan Ma + 4 more
Large Language Models of the Transformer architecture display great promise in automated code error detection based on their strength in processing sequential data. Nevertheless, their efficacy could be further improved by addressing the inherent weakness in handling structural code dependencies. In response to this…
Jeremy Li, Alex Rubinsteyn, Sergey Feldman, Timothy O’Donnell + 18 more
Scientific computing has become a central component of modern scientific discovery. Yet many computational tools are developed by small, specialized teams under incentives that encourage the release of rapidly prototyped tooling without commensurate attention to engineering concerns, including performance and…
Aaron Pfennig, Alexandre Lomsadze, Mark Borodovsky
Some of recently discovered in human gut microbiome highly divergent crAssphages were reported to use multiple genetic codes. Opal or amber stop codon reassignments were present in parts of the genomes, while the standard genetic code was used in the remaining genome sections. Essentially, the phage genomes were…
Samantha L. Peters, Adair L. Borges, Richard J. Giannone, Michael J. Morowitz + 2 more
Metagenomic findings suggesting that bacteriophages (phages) can use genetic codes different from those of their host bacteria reveal a new dimension of phage-host interaction dynamics. Whereas reassignment of stop codons to code for amino acids has been predicted, there has been no proteomic validation of alternative…